Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3872 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9293. Min Range: -3.9293

Max Act: 3.9293. Min Act: -0.0000

Data Index: 591084 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 3.9293. Min Range: -3.9293

Max Act: 3.8978. Min Act: -0.0000

Data Index: 1191791 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 3.9293. Min Range: -3.9293

Max Act: 3.3018. Min Act: -0.0000

Data Index: 747150 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 3.9293. Min Range: -3.9293

Max Act: 3.3479. Min Act: -0.0000

Data Index: 294706 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 3.9293. Min Range: -3.9293

Max Act: 3.0385. Min Act: -0.0000

Data Index: 506834 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.9989. Min Act: -0.0000

Data Index: 244752 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.9999. Min Act: -0.0000

Data Index: 830913 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 3.9293. Min Range: -3.9293

Max Act: 3.1415. Min Act: -0.0000

Data Index: 681912 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.9111. Min Act: -0.0000

Data Index: 545146 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.9979. Min Act: -0.0000

Data Index: 319764 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.6109. Min Act: -0.0000

Data Index: 1026563 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.7513. Min Act: -0.0000

Data Index: 783196 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.7611. Min Act: -0.0000

Data Index: 1012925 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.5796. Min Act: -0.0000

Data Index: 1290769 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.6848. Min Act: -0.0000

Data Index: 413771 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.6848. Min Act: -0.0000

Data Index: 1163415 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.5431. Min Act: -0.0000

Data Index: 277231 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.4130. Min Act: -0.0000

Data Index: 126775 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.5532. Min Act: -0.0000

Data Index: 928341 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 3.9293. Min Range: -3.9293

Max Act: 2.3927. Min Act: -0.0000

Data Index: 1001473 (C4 (Web Text))

Max Activating Token Index: 341